Distributed cooperative task allocation for heterogeneous UAV swarms under complex constraints

This paper investigates the dynamic task allocation problem for a heterogeneous UAV swarm conducting reconnaissance and strike (RAS) tasks while considering constraints on critical task time, communication range, and task resource requirements. The main challenge is to reconnaissance and strike all unknown targets within the mission area, which involves managing the UAV's changing states, task information, and variable communication with neighboring nodes. It is also important to overcome the limitations of current consensus-based heuristic task allocation approaches, which often lead to sub-optimal solutions due to being trapped in a local optimum within a distributed computing framework. To solve these problems, a novel heterogeneous UAV swarm task allocation model is developed first to maximize task benefits and minimize path planning costs. Second, we propose a two-phase consensus-based group bundling algorithm (CBGBA), which enables UAVs to reach consensus on task allocation results in a dynamic environment. In the task inclusion phase, we create feasible time slots for newly added tasks by optimizing task delay and sequence revenue, thus preventing the occurrence local optima problems under the critical task time constraint. In the consensus procedure phase, we employ a block-information-sharing (BIS) strategy to establish local networks, resolving consensus conflicts due to communication range constraints. Additionally, we propose an improved consensus principle that facilitates dynamic task allocation among distributed heterogeneous UAVs, meeting task resource requirements. Finally, the simulation results demonstrate the effectiveness and superiority of our proposed algorithm. Furthermore, CBGBA exhibits a performance enhancement of up to 14.2 % compared to the consensus-based synergy algorithm (CBSA).